Simulating and Evaluating Multi-Turn Conversations

This video demonstrates how to simulate and evaluate multi-turn conversations for AI chatbot systems. Follow along with the Jupyter notebook (https://langfuse.com/guides/cookbook/example-simulated-multi-turn-conversations) or with your own application traced in Langfuse. 00:00 Introduction to simulations and OpenEvals 00:43 Creating a dataset in Langfuse 02:16 Using OpenEvals with Langfuse Dataset Experiments 03:55 Using LLM-as-a-Judge to score the simulations 05:35 Summary